Newest papers

Diffusion Sensitivity Geometry and Strong Duality for Optimal Privacy-Utility Tradeoffs

Tue Do, Daniel Alabi · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28991 · cited by 0 works (OpenAlex) · open-access PDF

Korean

확산 모델에서 차별적 개인 정보 보호에 대한 기존 접근 방식은 느슨한 민감도 경계와 고스시아 소음에 의존하여 불필요한 추정 오류를 초래합니다. 우리는 최적의 개인 정보 유틸리티 거래를위한 프레임 워프를 개발하고 데이터 세트 크기에 상관없이 보수적 인 경계를 정확한 민감도 특징과 최적의 노이즈 캘리브레이션으로 대체합니다. 첫째, 우리는 임의의 크기의 데이터 세트에 대한 최악의 민감도가 정확하게 두 개의 레코드를 사용하여 특징화 될 수 있음을 보여줍니다. 둘째, Rényi, Approximate 및 Gaussian 차별적 개인 정보에 대한 정확한 개인 정보 보호 보증을 얻는 것은 데이터 세트 크기에 상관없이 최소 $m(

Machine translation (Meta M2M100); the English original follows.

Abstract

Existing approaches to differential privacy in diffusion models rely on loose sensitivity bounds and isotropic Gaussian noise, leading to unnecessary estimation error. We develop a framework for the optimal privacy-utility tradeoff of ideal diffusion denoisers, replacing conservative bounds with exact sensitivity characterizations and provably optimal noise calibration. First, we show that worst-case sensitivity over datasets of arbitrary size can be characterized exactly using only two records. For a data domain of size $m$, this reduces the analysis to at most $m(m-1)$ constraints, regardless of dataset size. Our characterization can be arbitrarily tighter than conventional diameter-based sensitivity bounds, revealing potentially unbounded improvements in noise calibration. Second, we obtain exact privacy guarantees for Rényi, approximate, and Gaussian differential privacy, as well as mutual-information privacy for binary records, avoiding the looseness of previous generic privacy conversions. Finally, we show that the minimum achievable weighted mean-squared error can be computed through a semidefinite program and prove strong duality, providing certificates of global optimality.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Sensitivity (control systems), Differential privacy, Duality (order theory), Gaussian, Mathematics, Noise (video)

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28991, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange